© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7724
    Prev
    Next
    INDEX
    Explanations

    math and code punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onaut
    -0.08
    оÑģÑĤо
    -0.08
    _]
    -0.08
    åıijçİ°åľ¨
    -0.08
    ÙĬÙij
    -0.08
    Ñģел
    -0.08
    evos
    -0.07
    è¸ıè¸ıå®ŀ
    -0.07
    ãģĿãĤĮãģ«
    -0.07
    NESS
    -0.07
    POSITIVE LOGITS
    æķ´
    0.07
    cope
    0.06
    opa
    0.06
    erso
    0.06
    ertz
    0.06
    å¥ij
    0.06
    æĭĻ
    0.06
    è¿ĻæĦıåij³çĿĢ
    0.06
    åį³
    0.06
    ä¸ŃæĮĩ
    0.06
    Activations Density 0.003%

    No Known Activations